From owner-cvs-all Wed Mar 12 14: 4:10 2003 Delivered-To: cvs-all@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 702A237B401; Wed, 12 Mar 2003 14:04:06 -0800 (PST) Received: from mta5.snfc21.pbi.net (mta5.snfc21.pbi.net [206.13.28.241]) by mx1.FreeBSD.org (Postfix) with ESMTP id B95EA43FAF; Wed, 12 Mar 2003 14:04:05 -0800 (PST) (envelope-from hsu@FreeBSD.org) Received: from FreeBSD.org ([63.193.112.125]) by mta5.snfc21.pbi.net (iPlanet Messaging Server 5.1 HotFix 1.6 (built Oct 18 2002)) with ESMTP id <0HBN00DUNPABZW@mta5.snfc21.pbi.net>; Wed, 12 Mar 2003 14:03:48 -0800 (PST) Date: Wed, 12 Mar 2003 14:04:22 -0800 From: Jeffrey Hsu Subject: Re: cvs commit: src/sys/netinet tcp_input.c In-reply-to: Message from Hiten Pandya "of Wed, 12 Mar 2003 16:01:07 EST." <20030312210107.GA56887@unixdaemons.com> To: Hiten Pandya Cc: src-committers@FreeBSD.ORG, cvs-src@FreeBSD.ORG, cvs-all@FreeBSD.ORG Message-id: <0HBN00DUOPABZW@mta5.snfc21.pbi.net> MIME-version: 1.0 X-Mailer: exmh version 2.5 07/13/2001 with nmh-1.0.4 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG >> hsu 2003/03/12 12:27:28 PST >> >> FreeBSD src repository >> >> Modified files: >> sys/netinet tcp_input.c >> Log: >> Implement the Limited Transmit algorithm (RFC 3042). > Can you elaborate on this? Sure. Quoting from RFC 3042: The "Limited Transmit" algorithm calls for sending a new data segment in response to each of the first two duplicate acknowledgments that arrive at the sender. Transmitting these segments increases the probability that TCP can recover from a single lost segment using the fast retransmit algorithm, rather than using a costly retransmission timeout. [BPS+97] found that roughly 56% of retransmissions sent by a busy web server were sent after the RTO expires, while only 44% were handled by Fast Retransmit. In addition, only 4% of the RTO-based retransmissions could have been avoided with SACK, which of course has to continue to disambiguate reordering from genuine loss. In contrast, using the technique outlined in this document and in [Bal98], 25% of the RTO-based retransmissions in that dataset would have likely been avoided. And from the tcp(4) man page: tcp.rfc3042 Enable the Limited Transmit algorithm as described in RFC 3042. It helps avoid timeouts on lossy links. This is a standards track RFC and is off by default. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message